Trigger an extract refresh on a workbook.
AI agents invoke refresh_workbook to trigger actions in Tableau MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Refreshing a workbook extract executes a backend operation that can consume computational resources, potentially lock data sources, trigger downstream dependencies, and cause availability or performance impacts. While not destructive or financial, it is an active trigger of external processes that qualifies as Execute.
From the tool's definition Tool description states 'Trigger an extract refresh on a workbook' — the word 'trigger' and 'refresh' indicate an active operation that initiates a process on an external system (Tableau Server/Cloud).
Attacks that exploit this kind of access
Trigger an extract refresh on a workbook. It is categorised as a Execute tool in the Tableau MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tableau MCP Server MCP server in PolicyLayer and add a rule for refresh_workbook: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Tableau MCP Server. Nothing to install.
refresh_workbook is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the refresh_workbook rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for refresh_workbook. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
refresh_workbook is provided by the Tableau MCP Server MCP server (lokimcpuniverse/tableau-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →